Deep neural network improves fracture detection by clinicians.

Suspected fractures are among the most common reasons for patients to visit emergency departments (EDs), and X-ray imaging is the primary diagnostic tool used by clinicians to assess patients for fractures. Missing a fracture in a radiograph often has severe consequences for patients, resulting in delayed treatment and poor recovery of function. Nevertheless, radiographs in emergency settings are often read out of necessity by emergency medicine clinicians who lack subspecialized expertise in orthopedics, and misdiagnosed fractures account for upward of four of every five reported diagnostic errors in certain EDs. In this work, we developed a deep neural network to detect and localize fractures in radiographs. We trained it to accurately emulate the expertise of 18 senior subspecialized orthopedic surgeons by having them annotate 135,409 radiographs. We then ran a controlled experiment with emergency medicine clinicians to evaluate their ability to detect fractures in wrist radiographs with and without the assistance of the deep learning model. The average clinician's sensitivity was 80.8% (95% CI, 76.7-84.1%) unaided and 91.5% (95% CI, 89.3-92.9%) aided, and specificity was 87.5% (95 CI, 85.3-89.5%) unaided and 93.9% (95% CI, 92.9-94.9%) aided. The average clinician experienced a relative reduction in misinterpretation rate of 47.0% (95% CI, 37.4-53.9%). The significant improvements in diagnostic accuracy that we observed in this study show that deep learning methods are a mechanism by which senior medical specialists can deliver their expertise to generalists on the front lines of medicine, thereby providing substantial improvements to patient care.

Severity of Agricultural Injuries and Its Economic Consequences in Border Belt of Gurdaspur District of Punjab, India.

OBJECTIVES: This study collected data related to agricultural injuries, analyzed their causes, and suggested possible remedial actions. Few studies from developing countries have investigated this important topic. Such investigations are extremely important and are required to frame national policies. METHODS: A well-designed structured form was developed to collect and evaluate data on agricultural incidents, their causes, the severity of injuries, and possible prevention methods. The authors followed a door-to-door survey methodology to collect data with the help of local village leaders. RESULTS: Less educated and older adults in the age group 31 to 45 years were more prone to agricultural incidents (p < .05). The mean age of the victims was 35.02 years (95% CI 32.7 to 37.3); 124 (91.18%) of the victims were men; and 21 (15.4%) of the cases were fatal. Tractor rollovers caused most of the deaths. Chaff cutters were responsible for most of the incidents that required amputation. Eighteen (45%) of the chaff-cutter incidents occurred in the evening between 3:00 PM and 6:00 PM, and 12 (30%) of these incidents occurred due to fatigue. CONCLUSIONS: The authors strongly recommend that rollover protective structures (ROPS) for tractors and seat belts should be made mandatory in India. Public guidelines emphasizing mandatory higher education for farmers and a model curriculum for both schools and colleges that focuses on the safety of rural populations should be developed. Special training should be provided on the safe operation of machinery and a definitive work - rest schedule should be followed to prevent fatigue and protect agricultural workers from incidents.

FastMRI Prostate: A public, biparametric MRI dataset to advance machine learning for prostate cancer imaging.

Magnetic resonance imaging (MRI) has experienced remarkable advancements in the integration of artificial intelligence (AI) for image acquisition and reconstruction. The availability of raw k-space data is crucial for training AI models in such tasks, but public MRI datasets are mostly restricted to DICOM images only. To address this limitation, the fastMRI initiative released brain and knee k-space datasets, which have since seen vigorous use. In May 2023, fastMRI was expanded to include biparametric (T2- and diffusion-weighted) prostate MRI data from a clinical population. Biparametric MRI plays a vital role in the diagnosis and management of prostate cancer. Advances in imaging methods, such as reconstructing under-sampled data from accelerated acquisitions, can improve cost-effectiveness and accessibility of prostate MRI. Raw k-space data, reconstructed images and slice, volume and exam level annotations for likelihood of prostate cancer are provided in this dataset for 47468 slices corresponding to 1560 volumes from 312 patients. This dataset facilitates AI and algorithm development for prostate image reconstruction, with the ultimate goal of enhancing prostate cancer diagnosis.

Predicting Risk of Alzheimer's Diseases and Related Dementias with AI Foundation Model on Electronic Health Records.

Early identification of Alzheimer's disease (AD) and AD-related dementias (ADRD) has high clinical significance, both because of the potential to slow decline through initiating FDA-approved therapies and managing modifiable risk factors, and to help persons living with dementia and their families to plan before cognitive loss makes doing so challenging. However, substantial racial and ethnic disparities in early diagnosis currently lead to additional inequities in care, urging accurate and inclusive risk assessment programs. In this study, we trained an artificial intelligence foundation model to represent the electronic health records (EHR) data with a vast cohort of 1.2 million patients within a large health system. Building upon this foundation EHR model, we developed a predictive Transformer model, named TRADE, capable of identifying risks for AD/ADRD and mild cognitive impairment (MCI), by analyzing the past sequential visit records. Amongst individuals 65 and older, our model was able to generate risk predictions for various future timeframes. On the held-out validation set, our model achieved an area under the receiver operating characteristic (AUROC) of 0.772 (95% CI: 0.770, 0.773) for identifying the AD/ADRD/MCI risks in 1 year, and AUROC of 0.735 (95% CI: 0.734, 0.736) in 5 years. The positive predictive values (PPV) in 5 years among individuals with top 1% and 5% highest estimated risks were 39.2% and 27.8%, respectively. These results demonstrate significant improvements upon the current EHR-based AD/ADRD/MCI risk assessment models, paving the way for better prognosis and management of AD/ADRD/MCI at scale.

Pancreatic Cystic Lesions: Next Generation of Radiologic Assessment.

Pancreatic cystic lesions are frequently identified on cross-sectional imaging. As many of these are presumed branch-duct intraductal papillary mucinous neoplasms, these lesions generate much anxiety for the patients and clinicians, often necessitating long-term follow-up imaging and even unnecessary surgical resections. However, the incidence of pancreatic cancer is overall low for patients with incidental pancreatic cystic lesions. Radiomics and deep learning are advanced tools of imaging analysis that have attracted much attention in addressing this unmet need, however, current publications on this topic show limited success and large-scale research is needed.

FastMRI Prostate: A Publicly Available, Biparametric MRI Dataset to Advance Machine Learning for Prostate Cancer Imaging.

The fastMRI brain and knee dataset has enabled significant advances in exploring reconstruction methods for improving speed and image quality for Magnetic Resonance Imaging (MRI) via novel, clinically relevant reconstruction approaches. In this study, we describe the April 2023 expansion of the fastMRI dataset to include biparametric prostate MRI data acquired on a clinical population. The dataset consists of raw k-space and reconstructed images for T2-weighted and diffusion-weighted sequences along with slice-level labels that indicate the presence and grade of prostate cancer. As has been the case with fastMRI, increasing accessibility to raw prostate MRI data will further facilitate research in MR image reconstruction and evaluation with the larger goal of improving the utility of MRI for prostate cancer detection and evaluation. The dataset is available at https://fastmri.med.nyu.edu.

A No-Math Primer on the Principles of Machine Learning for Radiologists.

Machine learning is becoming increasingly important in both research and clinical applications in radiology due to recent technological developments, particularly in deep learning. As these technologies are translated toward clinical practice, there is a need for radiologists and radiology trainees to understand the basic principles behind them. This primer provides an accessible introduction to the vocabulary and concepts that are central to machine learning and relevant to the radiologist.

Comparative evaluation of microleakage of metallic copings luted with three different commercially available luting cements: An in vitro study.

Aim: To evaluate the microleakage of metallic copings luted with three different commercially available luting cements. Setting and Design: Comparative evaluation in vitro study. Materials and Methods: Thirty replicas of abutment analog were milled and divided into 3 groups. Nickel chromium copings were fabricated; marginal gap was evaluated with optical microscope and luted with Zinc Oxide Non Eugenol cement, Zinc Polycarboxylate cement and Zinc Phosphate cement. After Thermocycling, cemented specimens were placed into 0.5% aqueous solution of basic fuchsin solution for 24 hours for dye penetration. Copings were longitudinally sectioned and microleakage scores were evaluated. Statistical Analysis Used: Kruskal-Wallis analysis of variance (ANOVA) followed by Chi-Square test. Pairwise comparison of groups with Mann Whitney U test. Result: Mean microleakage score was least for Zinc Phosphate cement (1.075 ± 0.85) followed by Zinc Polycarboxylate cement (1.80± 0.23) and most for Zinc Oxide Non Eugenol (2.1± 0.37). The results of the study were statistically significant, P < 0.05. Conclusions: Within the limitations of the study, it was found that all cements exhibited certain amount of microleakage. Zinc Phosphate cement exhibited a mean microleakage score that was significantly lower than Zinc Oxide Non Eugenol cement and Zinc Polycarboxylate cement. When microleakage scores of Zinc Oxide Non Eugenol cement and Zinc Polycarboxylate cement were compared, the difference was found to be insignificant indicating that microleakage in these cements is similar.

Surgical scar revision using silicone gel sheet as an adjunct.

INTRODUCTION: Scar is often referred to as an unattractive mark after healing of a wound. An undesirable scar may have negative social, emotional, and functional impact on the patient. It is our job as surgeons to adequately understand the expectations of the patient and counsel them for a successful procedure. MATERIALS AND METHODS: Twelve patients were randomly chosen for the study, of which five were males and seven were females. The scar tissue was removed surgically, and silicone gel sheets (SGSs) were applied on the 14th postoperative day, and the dimensions of the new scar was measured periodically up to 12 months. RESULTS: The study comprised of 12 patients- 5 males and 7 females. The descriptive statistics were calculated as median and interquartile range and comparison between time intervals was done using Wilcoxon signed rank test. Out of the 12 patients, 10 showing complete resolution of the scar and 2 patients had partial relapse of scar. However, they were satisfied with the final outcome. CONCLUSION: Our study found that SGSs applied to surgically revised scars significantly improves their appearance. The ease of use of the SGSs also makes it patient friendly. We observed almost complete resolution of the scar in ten patients and two patients exhibited partial relapse of the scar. However, there was a significant improvement in the overall appearance of the scar, and the patients were satisfied with the results of the procedure.

Assessment of a deep-learning system for fracture detection in musculoskeletal radiographs.

Missed fractures are the most common diagnostic error in emergency departments and can lead to treatment delays and long-term disability. Here we show through a multi-site study that a deep-learning system can accurately identify fractures throughout the adult musculoskeletal system. This approach may have the potential to reduce future diagnostic errors in radiograph interpretation.

Orbital floor dermoid: an unusual presentation.

Dermoid cysts are developmental abnormal arrangement of tissues and are often evident soon after birth. Its occurrence in the orbit is relatively rare. We report a case of orbital floor dermoid in an 18-year-old female patient who presented with progressive, painless swelling in the lower eyelid associated with mild proptosis of three months duration. The lesion was excised completely, and histopathology confirmed the diagnosis of dermoid cyst.

Sickle cell crisis leading to extensive necrosis in a low-grade glioma and masquerading high-grade lesion.

A 9-year-old female child presented with rapid neurological deterioration. Clinical features and imaging findings were suggestive of high-grade malignancy, and hematological investigations were suggestive of sickle cell trait. Histopathology showed features of low-grade malignancy and extensive intratumoral sickling. We hypothesize that the vicious cycle of hypoxia, sickling, thrombosis, ischemia and infarction resulted in the extensive tumor necrosis in the present case causing the initial symptoms and rapid deterioration in the condition of the patient.

Direct Maxillary Sinus Floor Augmentation for Simultaneous Dental Implant Placement.

AIM: The present study was done to evaluate the efficacy of platelet-rich fibrin (PRF) with bovine bone graft (Bio-Oss™) in direct sinus augmentation for simultaneously dental implant placement. MATERIALS AND METHODS: The study included 14 patients who fulfill the inclusion criteria, among them 10 were male and 4 were female with PRF with Bio-Oss™. For each patient, bone level was assessed preoperatively and postoperatively after 1, 6, and 12 months with a panoramic X-ray and radiovisiography to evaluate the vertical bone height from the shoulder of the implant to the most apical end. RESULTS: The outcome of the sinus lift and the implants placed was evaluated periodically at 1, 6, and 12 months postoperatively. All the patients underwent two-stage procedures. At the end of 20th week, implants were exposed; radiological parameters were assessed again for implant integration, and prosthetic rehabilitation was started after 2 weeks and it was completed by the end of 24 weeks (6 months postoperatively). Twelve months postoperatively, the endosinus bone gain noted was 7 mm, which indicated the use of PRF with bovine bone graft as a reliable filling material during simultaneous sinus lift and implantation. CONCLUSION: PRF with bone graft (Bio-Oss) is used as an augmentation material after direct maxillary sinus lift, and the resulting bone formation was adequate for placement of dental implant.

Orofacial space infection due to faulty prosthesis.

Orofacial space infections are commonly treated by oral and maxillofacial surgeons, even in the post antibiotic era. Pre existing systemic conditions such as diabetes mellitus makes a person more vulnerable to space infection. A prosthesis which is poorly designed often jeopardises the oral health and makes a person susceptible to ulcers of mucosa, which can result in necrosis of mucosa. The sequel of such ulcerations and necrosis would be life threatening Orofacial space infections in medically compromised patients. Here we present a case report of 64 year old diabetic patient presenting with Orofacial space infection as a sequel to necrosis of mucosa caused due to physical and chemical injury by a faulty prosthesis fabricated by a quack practicing dentistry. Submandibular, sublingual and pterygomandibular space were involved leading to trismus and swelling. On forceful mouth opening after extraoral mandibular nerve block, denudation of mucosa was seen distal and lingual to mandibular right second premolar with pus discharge. Radiographic examination revealed no abnormal findings in teeth or bone. The spaces were explored from the opening created by denuded mucosa. Infection control and diabetic control was achieved with antibiotics and oral hypoglycaemic drugs. Patient responded well for the treatment and recovered uneventfully.

A tender swelling of the left posterior mandible: An unusual case.

Tender swellings of the mandible are majorly due to inflammatory lesions like infected dental cyst, peri-apical abscess or neoplasms like osteoblastomas, cementoblastomas, osteosarcoma and intraosseous squamous cell carcinoma. Florid cemento-osseous dysplasia is a subgroup of cemento-osseous dysplasia typically found in middle-aged black women as multiple, non-tender, diffuse, lobulated radio-opacities distributed throughout the maxilla and mandible, which are usually bilaterally symmetrical. Histologically, they are composed of proliferating fibrous connective tissue stroma containing foci of cementum, osteoid and bone. Florid cemento-osseous dysplasia is rare in Indian population and among all cases of florid cemento-osseous dysplasia, almost 97% of the cases reported till date are in females. The present case describes florid cemento-osseous dysplasia in a 26-year-old male who reported with pain in the left mandibular premolar region.